Researchers from Boston Children’s Hospital are using cloud-based data from electronic medical records, in combination with data from other sources including Google, to pick up cases of influenza in real time, enhancing the Centers for Disease Control and Prevention’s reporting.
For their study, just published in the journal Scientific Reports, researchers tapped data from health IT vendor athenahealth. The company’s database encompassed more than 72,000 healthcare providers and EHRs for more than 23 million patients, mostly seen in office-based settings.
The investigators first trained the flu-prediction algorithm, called ARES, with data on weekly total visit counts, visit counts for flu and flu-like illness, visit counts for flu vaccination and other data captured from June 2009 through January 2012. They then used ARES to estimate flu activity over the next three years.
ARES’ estimates of national and regional flu activity had error rates 2- to 3-fold lower than earlier predictive models. ARES also correctly estimated the timing and magnitude of the national flu peak week, the researchers reported.
“We are incorporating the measurements used for weather forecasting that will lead to better predictions of what may happen tomorrow. That process, called data assimilation, is one in which you have your models, but you keep fine-tuning them as you get more information in real time,” explained lead study author, Mauricio Santillana, faculty member at Boston Children’s Computational Health Informatics Program (CHIP) and at Harvard Medical School.
“Your models become better at learning the relationship between the variables you are using as predictors. We use machine algorithms to continuously recalibrate our models so they produce the most accurate results,” Santillana said.
A Deep-dive Into Specialty Pharma
A specialty drug is a class of prescription medications used to treat complex, chronic or rare medical conditions. Although this classification was originally intended to define the treatment of rare, also termed “orphan” diseases, affecting fewer than 200,000 people in the US, more recently, specialty drugs have emerged as the cornerstone of treatment for chronic and complex diseases such as cancer, autoimmune conditions, diabetes, hepatitis C, and HIV/AIDS.
Athenahealth provides new, aggregated data to the research team every Monday. “They send us a new count of people who were sick, and who were seeking medical attention,” Santillana said. The arrangement essentially allows physicians to report flu symptoms in near-real time, he added.
Google, which in August 2015 ceased Google Flu Trends, a real-time system that tracked outbreaks by mining Internet searches, is also supplying data for the researchers’ work. While Google pulled the plug on Flu Trends after its estimates proved inaccurate, the company’s records are still useful. “Google gives us access to data that is not necessarily available to everyone so we can produce better estimates,” Santillana said.
The researchers also are collaborating with CDC, reporting flu estimates to the agency in real time, Santillana said.
Photo: Flickr user Claus Rebler
